Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.76
    astéroïdes
    -0.61
    wpi
    -0.60
     الدولى
    -0.57
    ScopeManager
    -0.54
    SourceChecksum
    -0.54
     referenties
    -0.50
    ρας
    -0.50
     Unito
    -0.50
    fony
    -0.49
    POSITIVE LOGITS
    Rptr
    0.59
    ParseTree
    0.52
    Dislikes
    0.52
    openConnection
    0.49
    beit
    0.48
    Diwedd
    0.48
    UnsafeEnabled
    0.48
    ANTLR
    0.48
    elemField
    0.48
    ourcing
    0.47
    Act Density 1.378%

    No Known Activations